Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1370 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.8457. Min Act: -0.0000

Data Index: 1457003 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.9887. Min Act: -0.0000

Data Index: 1549226 (Python Code)

Max Activating Token Index: 282

Text #2

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.6863. Min Act: -0.0000

Data Index: 1610464 (Python Code)

Max Activating Token Index: 267

Text #3

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.6472. Min Act: -0.0000

Data Index: 1458857 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.6331. Min Act: -0.0000

Data Index: 1394621 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.5027. Min Act: -0.0000

Data Index: 1476197 (Python Code)

Max Activating Token Index: 747

Text #6

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.4783. Min Act: -0.0000

Data Index: 1424384 (Python Code)

Max Activating Token Index: 883

Text #7

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1529019 (Python Code)

Max Activating Token Index: 117

Text #8

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.4062. Min Act: -0.0000

Data Index: 1651081 (Python Code)

Max Activating Token Index: 904

Text #9

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1467610 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.3883. Min Act: -0.0000

Data Index: 1517652 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1489538 (Python Code)

Max Activating Token Index: 369

Text #12

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1595650 (Python Code)

Max Activating Token Index: 399

Text #13

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1599250 (Python Code)

Max Activating Token Index: 737

Text #14

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.4578. Min Act: -0.0000

Data Index: 1529652 (Python Code)

Max Activating Token Index: 422

Text #15

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1400984 (Python Code)

Max Activating Token Index: 752

Text #16

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.3591. Min Act: -0.0000

Data Index: 1390817 (Python Code)

Max Activating Token Index: 379

Text #17

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1533484 (Python Code)

Max Activating Token Index: 393

Text #18

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.3173. Min Act: -0.0000

Data Index: 1609228 (Python Code)

Max Activating Token Index: 134

Text #19

Max Range: 1.9887. Min Range: -1.9887

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1657092 (Python Code)

Max Activating Token Index: 464